Primary Questions Are
- Are there differences between locations in mean land size?
- Is land-size important for determining food security or
incomes?
- How much does land size vary in one single location?
- Does predicting the mean, or the median actually tell us
anything?
- Can we interactively plot the marginal distribution of land-size,
given parameters in a given location?
- If so, can we combine this with census data to answer the question:
based on the data we have, we think there are N farmers with
farm-sizes under X ha, with confidence y
- How would we validate such a model?
Assessing Data Coverage and Completeness
We are interested in the distribution of farm characteristics at the
subnational level. To assess a “distribution”, we would need a
sufficient number of households.



Based on the plots above, there are three candidates from the
datasets which have helpful characteristics:
- They have a relatively large number of surveys (n>2000)
- They have surveys in a significant portion of their subnational
areas (>40%)
The three countries are Burkina Faso (West Africa), Rwanda (Central
Africa), and Tanzania (East Africa).
Land Size
In this study, we are interested in looking at Land Size. Land size
is an interesting variable to look at for smallholder farmers. It can
tell us a lot about other variables (some of which are more error prone,
or more difficult to measure e.g. income and food security).



Here we see that there might be some relationship between land size
and total income, food security, and livestock holdings.
Interestingly we see that the spread varies for different quantiles.
For example, for higher land sizes, we see a larger spread in income
values.
Spread of Land Sizes
In mapping efforts, we often see researchers trying to map averages.
For example, in the Lowder
article, they mapped average farm size per subnational unit using census
information, and information on the total arable land.
In different areas however, there is a large variation in land sizes.
Here we see that we have a wide range of land size distributions, each
of which vary quite significantly by country.





If we were to use land size to prioritise development interventions,
it would be important to account for the characteristics of land size
distributions.
Here we see that as the mean land size increases increases, so does
the standard deviation (same goes for the median and IQR).
We also see that for most subnational areas, Land Size distributions
are skewed, and in many of these areas the distributions are fat-tailed
(normal distribution has kurtosis of ~ 3)
What does this mean in practice. Lets say we are using Land Size to
target funding towards the poorest of the poor.


## [1] 3.141593
Subnational Level Covariates